Recent Progress on Generative Adversarial Networks (GANs): A Survey

Zhaoqing Pan, Weijie Yu, Xiaokai Yi, Asifullah Khan, Yuan Feng, Yuhui ZhengIEEE Access 2019 · DOI

Abstract

Generative adversarial networks (GANs) represent one of the most significant research avenues in artificial intelligence, noted for their exceptional data generation capabilities. This paper reviews recent progress in the field, analyzing the basic theory of GANs and comparing them with other generative models. We classify derived GAN models, discuss training heuristics and evaluation metrics, and explore diverse applications. Finally, we address current challenges and outline future research directions.

Introduction

Since Ian Goodfellow’s seminal 2014 paper, GANs have become a cornerstone of unsupervised learning. Despite their success, they are notoriously difficult to train, facing hurdles such as training instability and mode collapse. The rapid expansion of the "GAN zoo" (including variants like DCGAN, WGAN, and CycleGAN) has made it challenging for researchers to track which innovations address specific problems. This survey provides a taxonomy of these developments, tracing the evolution from basic theory to state-of-the-art applications in computer vision and beyond.

Basic GAN architecture showing the adversarial relationship between the Generator (G) and Discriminator (D).

Taxonomy of GAN Developments

The progress of GAN research can be categorized into three primary pillars: architecture optimization, objective function refinement, and training heuristics.

Architecture Optimization

Early GANs relied on simple Multi-Layer Perceptrons (MLPs). A major breakthrough came with Deep Convolutional GANs (DCGANs), which utilized convolutional layers to stabilize training for high-dimensional image data.

The DCGAN architecture, which replaced fully connected layers with convolutional layers to improve image synthesis.

Further advancements introduced control mechanisms, such as Conditional GANs (CGANs) and InfoGANs, which guide the generation process by incorporating auxiliary information or maximizing mutual information to disentangle latent variables. Hybrid models like Adversarial Autoencoders (AAE) and BiGANs combine the generative power of GANs with the reconstruction capabilities of autoencoders.

Objective Function Optimization

The original GAN formulation utilized Jensen-Shannon (JS) divergence, which often leads to vanishing gradients when the discriminator is too strong. The field has shifted toward Wasserstein GANs (WGAN) and its variants (WGAN-GP, WGAN-LP), which employ the "Earth-Mover" distance. This approach provides more reliable gradients and significantly improves training stability.

Training Heuristics

Practitioners have developed several "tricks of the trade" to stabilize the adversarial game. Key techniques include Label Smoothing, Minibatch Discrimination, Spectral Normalization, and the Two-Time-Scale Update Rule (TTUR). These methods help balance the learning rates of the generator and discriminator, preventing one from dominating the other prematurely.

Datasets and Evaluation

GAN models are typically validated on standard benchmarks:

  • ImageNet: Used for high-resolution synthesis (e.g., BigGAN).
  • CelebA: The standard for face synthesis and attribute manipulation.
  • MNIST/CIFAR-10: Common baseline datasets for testing new architectures.
  • Domain-Specific Data: Applications extend to medical imaging (AnoGAN), DNA sequences, and malware detection.

Evaluation remains a challenge. While the Inception Score (IS) measures quality and diversity, it can be misled. The Frechet Inception Distance (FID) is more robust but requires large sample sizes for accurate estimation.

Key Insights and Results

A critical realization in the field was the trade-off between Variational Autoencoders (VAEs) and GANs: VAEs offer stability but produce blurry outputs, whereas GANs yield high-fidelity, sharp images at the cost of training complexity.

Significant milestones include:

  • BigGAN: Achieved state-of-the-art performance on ImageNet with an IS of 166.3 and an FID of 9.6.
  • ESRGAN: Set new standards in super-resolution by recovering fine textures.
  • CycleGAN: Revolutionized style transfer by enabling domain translation (e.g., horse to zebra) using unpaired datasets.

Conclusion and Future Directions

Despite remarkable progress, GANs still struggle with mode collapse and discrete data types (e.g., text in NLP). A gap remains between empirical success and theoretical understanding. Future research is expected to focus on integrating GANs with Reinforcement Learning and advancing Semi-Supervised Learning to reduce reliance on massive labeled datasets.

Summary updated

Abstract

Generative adversarial network (GANs) is one of the most important research avenues in the field of artificial intelligence, and its outstanding data generation capacity has received wide attention. In this paper, we present the recent progress on GANs. First, the basic theory of GANs and the differences among different generative models in recent years were analyzed and summarized. Then, the derived models of GANs are classified and introduced one by one. Third, the training tricks and evaluation metrics were given. Fourth, the applications of GANs were introduced. Finally, the problem, we need to address, and future directions were discussed.
BibTeX
@inproceedings{pan2019recent,
  author = {Zhaoqing Pan and Weijie Yu and Xiaokai Yi and Asifullah Khan and Yuan Feng and Yuhui Zheng},
  title = {{Recent Progress on Generative Adversarial Networks (GANs): A Survey}},
  booktitle = {IEEE Access},
  year = {2019},
  doi = {10.1109/access.2019.2905015},
}
Figure